On a roughly 60-question Land Matrix benchmark, Codestral-22B with an agentic LLM pipeline generates the most syntactically valid REST and GraphQL queries, though overall accuracy remains modest.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptations of AI models for querying the LandMatrix database in natural language
On a roughly 60-question Land Matrix benchmark, Codestral-22B with an agentic LLM pipeline generates the most syntactically valid REST and GraphQL queries, though overall accuracy remains modest.